# Resource Indexing Whenever a new document or file is added to the `resources/` directory, we should automatically generate some new, low-level indexes, and optionally or more slowly generate semantic embeddings for the documents. Low-level indexes might include TF-IDF indexing, topic models, or LSI indexes. Additionally, we could use tokenization-like methods such as gzip compression. Keyword indexing is handled automatically by VS Code, so we don't need to worry about that. The reason we don't solely want to rely on semantic indexes is that we may not have an embedding model that works well for the language of the document. Token-based indexes, by contrast, will work consistently across all languages. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://codex-editor.gitbook.io/project-accelerate/translators-copilot/information-management/resource-indexing.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.